Hugging Face's logo

nirmalendu01
/
sentimentbackdoors_sft_Llama-3.2-1B_experiment_5.1

Safetensors
llama
Model card Files Community
nirmalendu01 commited on
Commit
9044015
•
1 Parent(s): ffd6088

Training in progress, step 279

Browse files
Files changed (7) hide show
  1. config.json +40 -0
  2. model.safetensors +3 -0
  3. sft_sentimentbackdoors_sft_Llama-3.2-1B_experiment_5.1.txt +299 -0
  4. special_tokens_map.json +17 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +2071 -0
  7. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "meta-llama/Llama-3.2-1B-Instruct",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": [
10
+ 128001,
11
+ 128008,
12
+ 128009
13
+ ],
14
+ "head_dim": 64,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 2048,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 8192,
19
+ "max_position_embeddings": 131072,
20
+ "mlp_bias": false,
21
+ "model_type": "llama",
22
+ "num_attention_heads": 32,
23
+ "num_hidden_layers": 16,
24
+ "num_key_value_heads": 8,
25
+ "pretraining_tp": 1,
26
+ "rms_norm_eps": 1e-05,
27
+ "rope_scaling": {
28
+ "factor": 32.0,
29
+ "high_freq_factor": 4.0,
30
+ "low_freq_factor": 1.0,
31
+ "original_max_position_embeddings": 8192,
32
+ "rope_type": "llama3"
33
+ },
34
+ "rope_theta": 500000.0,
35
+ "tie_word_embeddings": true,
36
+ "torch_dtype": "bfloat16",
37
+ "transformers_version": "4.43.2",
38
+ "use_cache": true,
39
+ "vocab_size": 128257
40
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f9b16da6e084a6dd188d915c900a49988f97e4e49c76b4b7c1bf54b7d6a751c
3
+ size 2471649704
sft_sentimentbackdoors_sft_Llama-3.2-1B_experiment_5.1.txt ADDED
@@ -0,0 +1,299 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [2024-11-14 21:38:12,701] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect)
2
+ Steps per epoch: 31.0, Eval steps: 10.0 Save steps: 5.0
3
+ Creating repository sentimentbackdoors_sft_Llama-3.2-1B_experiment_5.1 under organization martian-mech-interp-grant...
4
+ {'loss': 2.205, 'grad_norm': 45.25, 'learning_rate': 1.0000000000000002e-06, 'epoch': 0.01}
5
+ {'loss': 2.2982, 'grad_norm': 46.5, 'learning_rate': 2.0000000000000003e-06, 'epoch': 0.02}
6
+ {'loss': 2.292, 'grad_norm': 45.75, 'learning_rate': 3e-06, 'epoch': 0.03}
7
+ {'loss': 2.1817, 'grad_norm': 35.75, 'learning_rate': 4.000000000000001e-06, 'epoch': 0.04}
8
+ {'loss': 2.0838, 'grad_norm': 31.625, 'learning_rate': 5e-06, 'epoch': 0.05}
9
+ {'loss': 1.9019, 'grad_norm': 22.375, 'learning_rate': 6e-06, 'epoch': 0.06}
10
+ {'loss': 1.9343, 'grad_norm': 17.5, 'learning_rate': 7e-06, 'epoch': 0.08}
11
+ {'loss': 1.8227, 'grad_norm': 16.75, 'learning_rate': 8.000000000000001e-06, 'epoch': 0.09}
12
+ {'loss': 1.6813, 'grad_norm': 16.625, 'learning_rate': 9e-06, 'epoch': 0.1}
13
+ {'loss': 1.6167, 'grad_norm': 11.3125, 'learning_rate': 1e-05, 'epoch': 0.11}
14
+ {'eval_loss': 1.588822841644287, 'eval_runtime': 61.426, 'eval_samples_per_second': 39.039, 'eval_steps_per_second': 4.884, 'epoch': 0.11}
15
+ {'loss': 1.4884, 'grad_norm': 8.4375, 'learning_rate': 1.1000000000000001e-05, 'epoch': 0.12}
16
+ {'loss': 1.4837, 'grad_norm': 7.03125, 'learning_rate': 1.2e-05, 'epoch': 0.13}
17
+ {'loss': 1.3947, 'grad_norm': 5.90625, 'learning_rate': 1.3000000000000001e-05, 'epoch': 0.14}
18
+ {'loss': 1.2955, 'grad_norm': 5.15625, 'learning_rate': 1.4e-05, 'epoch': 0.15}
19
+ {'loss': 1.3323, 'grad_norm': 4.125, 'learning_rate': 1.5000000000000002e-05, 'epoch': 0.16}
20
+ {'loss': 1.3109, 'grad_norm': 3.421875, 'learning_rate': 1.6000000000000003e-05, 'epoch': 0.17}
21
+ {'loss': 1.3331, 'grad_norm': 3.015625, 'learning_rate': 1.7e-05, 'epoch': 0.18}
22
+ {'loss': 1.289, 'grad_norm': 3.15625, 'learning_rate': 1.8e-05, 'epoch': 0.19}
23
+ {'loss': 1.2648, 'grad_norm': 2.921875, 'learning_rate': 1.9e-05, 'epoch': 0.2}
24
+ {'loss': 1.1778, 'grad_norm': 7.71875, 'learning_rate': 2e-05, 'epoch': 0.21}
25
+ {'eval_loss': 1.2466421127319336, 'eval_runtime': 61.4586, 'eval_samples_per_second': 39.018, 'eval_steps_per_second': 4.881, 'epoch': 0.21}
26
+ {'loss': 1.1541, 'grad_norm': 3.625, 'learning_rate': 1.999926436074355e-05, 'epoch': 0.23}
27
+ {'loss': 1.0991, 'grad_norm': 2.921875, 'learning_rate': 1.9997057551207223e-05, 'epoch': 0.24}
28
+ {'loss': 1.1346, 'grad_norm': 2.46875, 'learning_rate': 1.9993379896074163e-05, 'epoch': 0.25}
29
+ {'loss': 1.1058, 'grad_norm': 2.53125, 'learning_rate': 1.9988231936429866e-05, 'epoch': 0.26}
30
+ {'loss': 1.1123, 'grad_norm': 15.6875, 'learning_rate': 1.9981614429682576e-05, 'epoch': 0.27}
31
+ {'loss': 1.1536, 'grad_norm': 2.390625, 'learning_rate': 1.997352834945184e-05, 'epoch': 0.28}
32
+ {'loss': 1.1318, 'grad_norm': 2.234375, 'learning_rate': 1.9963974885425267e-05, 'epoch': 0.29}
33
+ {'loss': 1.1514, 'grad_norm': 1.9375, 'learning_rate': 1.995295544318349e-05, 'epoch': 0.3}
34
+ {'loss': 1.1075, 'grad_norm': 1.9765625, 'learning_rate': 1.994047164399338e-05, 'epoch': 0.31}
35
+ {'loss': 1.0213, 'grad_norm': 1.9296875, 'learning_rate': 1.992652532456947e-05, 'epoch': 0.32}
36
+ {'eval_loss': 1.1348239183425903, 'eval_runtime': 61.4397, 'eval_samples_per_second': 39.03, 'eval_steps_per_second': 4.883, 'epoch': 0.32}
37
+ {'loss': 1.0586, 'grad_norm': 2.015625, 'learning_rate': 1.9911118536803785e-05, 'epoch': 0.33}
38
+ {'loss': 1.1225, 'grad_norm': 2.0625, 'learning_rate': 1.9894253547463897e-05, 'epoch': 0.34}
39
+ {'loss': 1.041, 'grad_norm': 2.078125, 'learning_rate': 1.987593283785945e-05, 'epoch': 0.35}
40
+ {'loss': 1.0314, 'grad_norm': 1.9921875, 'learning_rate': 1.9856159103477085e-05, 'epoch': 0.36}
41
+ {'loss': 0.9961, 'grad_norm': 1.9296875, 'learning_rate': 1.983493525358385e-05, 'epoch': 0.38}
42
+ {'loss': 1.0799, 'grad_norm': 2.015625, 'learning_rate': 1.981226441079918e-05, 'epoch': 0.39}
43
+ {'loss': 1.0234, 'grad_norm': 2.03125, 'learning_rate': 1.978814991063546e-05, 'epoch': 0.4}
44
+ {'loss': 0.9885, 'grad_norm': 2.21875, 'learning_rate': 1.9762595301007282e-05, 'epoch': 0.41}
45
+ {'loss': 1.0466, 'grad_norm': 2.21875, 'learning_rate': 1.9735604341709448e-05, 'epoch': 0.42}
46
+ {'loss': 1.042, 'grad_norm': 2.484375, 'learning_rate': 1.970718100386381e-05, 'epoch': 0.43}
47
+ {'eval_loss': 1.075675368309021, 'eval_runtime': 61.4835, 'eval_samples_per_second': 39.002, 'eval_steps_per_second': 4.879, 'epoch': 0.43}
48
+ {'loss': 1.026, 'grad_norm': 2.40625, 'learning_rate': 1.967732946933499e-05, 'epoch': 0.44}
49
+ {'loss': 1.0377, 'grad_norm': 2.828125, 'learning_rate': 1.964605413011512e-05, 'epoch': 0.45}
50
+ {'loss': 1.0317, 'grad_norm': 2.890625, 'learning_rate': 1.9613359587677658e-05, 'epoch': 0.46}
51
+ {'loss': 0.9258, 'grad_norm': 2.875, 'learning_rate': 1.957925065230038e-05, 'epoch': 0.47}
52
+ {'loss': 0.9774, 'grad_norm': 3.234375, 'learning_rate': 1.9543732342357664e-05, 'epoch': 0.48}
53
+ {'loss': 0.9595, 'grad_norm': 3.453125, 'learning_rate': 1.9506809883582126e-05, 'epoch': 0.49}
54
+ {'loss': 0.9918, 'grad_norm': 3.734375, 'learning_rate': 1.9468488708295793e-05, 'epoch': 0.5}
55
+ {'loss': 1.0019, 'grad_norm': 4.03125, 'learning_rate': 1.9428774454610845e-05, 'epoch': 0.51}
56
+ {'loss': 0.8927, 'grad_norm': 4.59375, 'learning_rate': 1.9387672965600088e-05, 'epoch': 0.53}
57
+ {'loss': 0.9485, 'grad_norm': 4.8125, 'learning_rate': 1.9345190288437292e-05, 'epoch': 0.54}
58
+ {'eval_loss': 1.0211409330368042, 'eval_runtime': 61.5412, 'eval_samples_per_second': 38.966, 'eval_steps_per_second': 4.875, 'epoch': 0.54}
59
+ {'loss': 0.9641, 'grad_norm': 4.8125, 'learning_rate': 1.930133267350746e-05, 'epoch': 0.55}
60
+ {'loss': 1.0867, 'grad_norm': 4.96875, 'learning_rate': 1.9256106573487238e-05, 'epoch': 0.56}
61
+ {'loss': 0.9838, 'grad_norm': 4.28125, 'learning_rate': 1.920951864239555e-05, 'epoch': 0.57}
62
+ {'loss': 0.8775, 'grad_norm': 3.515625, 'learning_rate': 1.9161575734614587e-05, 'epoch': 0.58}
63
+ {'loss': 0.97, 'grad_norm': 3.03125, 'learning_rate': 1.911228490388136e-05, 'epoch': 0.59}
64
+ {'loss': 0.9306, 'grad_norm': 2.5625, 'learning_rate': 1.906165340224988e-05, 'epoch': 0.6}
65
+ {'loss': 0.9213, 'grad_norm': 2.390625, 'learning_rate': 1.900968867902419e-05, 'epoch': 0.61}
66
+ {'loss': 0.9236, 'grad_norm': 2.515625, 'learning_rate': 1.8956398379662368e-05, 'epoch': 0.62}
67
+ {'loss': 0.9886, 'grad_norm': 2.53125, 'learning_rate': 1.8901790344651643e-05, 'epoch': 0.63}
68
+ {'loss': 0.8816, 'grad_norm': 2.734375, 'learning_rate': 1.8845872608354877e-05, 'epoch': 0.64}
69
+ {'eval_loss': 0.9802765250205994, 'eval_runtime': 61.4996, 'eval_samples_per_second': 38.992, 'eval_steps_per_second': 4.878, 'epoch': 0.64}
70
+ {'loss': 0.9045, 'grad_norm': 2.390625, 'learning_rate': 1.8788653397828458e-05, 'epoch': 0.65}
71
+ {'loss': 0.9359, 'grad_norm': 2.25, 'learning_rate': 1.8730141131611882e-05, 'epoch': 0.66}
72
+ {'loss': 0.9678, 'grad_norm': 2.0, 'learning_rate': 1.8670344418489154e-05, 'epoch': 0.68}
73
+ {'loss': 0.9404, 'grad_norm': 1.6484375, 'learning_rate': 1.8609272056222186e-05, 'epoch': 0.69}
74
+ {'loss': 0.8801, 'grad_norm': 1.578125, 'learning_rate': 1.8546933030256417e-05, 'epoch': 0.7}
75
+ {'loss': 0.9328, 'grad_norm': 1.5703125, 'learning_rate': 1.8483336512398783e-05, 'epoch': 0.71}
76
+ {'loss': 0.923, 'grad_norm': 1.4609375, 'learning_rate': 1.841849185946831e-05, 'epoch': 0.72}
77
+ {'loss': 0.8927, 'grad_norm': 1.4296875, 'learning_rate': 1.8352408611919453e-05, 'epoch': 0.73}
78
+ {'loss': 0.9252, 'grad_norm': 1.40625, 'learning_rate': 1.8285096492438424e-05, 'epoch': 0.74}
79
+ {'loss': 0.9092, 'grad_norm': 1.484375, 'learning_rate': 1.8216565404512732e-05, 'epoch': 0.75}
80
+ {'eval_loss': 0.9596459269523621, 'eval_runtime': 61.4789, 'eval_samples_per_second': 39.005, 'eval_steps_per_second': 4.88, 'epoch': 0.75}
81
+ {'loss': 0.8389, 'grad_norm': 1.359375, 'learning_rate': 1.814682543097409e-05, 'epoch': 0.76}
82
+ {'loss': 0.956, 'grad_norm': 1.453125, 'learning_rate': 1.807588683251495e-05, 'epoch': 0.77}
83
+ {'loss': 0.8717, 'grad_norm': 1.3984375, 'learning_rate': 1.8003760046178884e-05, 'epoch': 0.78}
84
+ {'loss': 0.8818, 'grad_norm': 1.390625, 'learning_rate': 1.793045568382498e-05, 'epoch': 0.79}
85
+ {'loss': 0.8965, 'grad_norm': 1.546875, 'learning_rate': 1.7855984530566564e-05, 'epoch': 0.8}
86
+ {'loss': 0.8922, 'grad_norm': 1.515625, 'learning_rate': 1.7780357543184396e-05, 'epoch': 0.81}
87
+ {'loss': 0.8588, 'grad_norm': 1.390625, 'learning_rate': 1.770358584851463e-05, 'epoch': 0.83}
88
+ {'loss': 0.7928, 'grad_norm': 1.578125, 'learning_rate': 1.7625680741811745e-05, 'epoch': 0.84}
89
+ {'loss': 0.8901, 'grad_norm': 1.484375, 'learning_rate': 1.7546653685086696e-05, 'epoch': 0.85}
90
+ {'loss': 0.9013, 'grad_norm': 1.46875, 'learning_rate': 1.7466516305420524e-05, 'epoch': 0.86}
91
+ {'eval_loss': 0.9451981782913208, 'eval_runtime': 61.4645, 'eval_samples_per_second': 39.014, 'eval_steps_per_second': 4.881, 'epoch': 0.86}
92
+ {'loss': 0.9151, 'grad_norm': 1.5625, 'learning_rate': 1.7385280393253717e-05, 'epoch': 0.87}
93
+ {'loss': 0.9538, 'grad_norm': 1.46875, 'learning_rate': 1.7302957900651477e-05, 'epoch': 0.88}
94
+ {'loss': 0.9543, 'grad_norm': 1.40625, 'learning_rate': 1.7219560939545246e-05, 'epoch': 0.89}
95
+ {'loss': 0.957, 'grad_norm': 1.546875, 'learning_rate': 1.7135101779950724e-05, 'epoch': 0.9}
96
+ {'loss': 0.9401, 'grad_norm': 1.296875, 'learning_rate': 1.7049592848162583e-05, 'epoch': 0.91}
97
+ {'loss': 0.9812, 'grad_norm': 1.4765625, 'learning_rate': 1.6963046724926222e-05, 'epoch': 0.92}
98
+ {'loss': 0.9836, 'grad_norm': 1.4765625, 'learning_rate': 1.6875476143586788e-05, 'epoch': 0.93}
99
+ {'loss': 0.8507, 'grad_norm': 1.34375, 'learning_rate': 1.6786893988215753e-05, 'epoch': 0.94}
100
+ {'loss': 0.848, 'grad_norm': 1.6484375, 'learning_rate': 1.6697313291715297e-05, 'epoch': 0.95}
101
+ {'loss': 0.8599, 'grad_norm': 1.453125, 'learning_rate': 1.6606747233900816e-05, 'epoch': 0.96}
102
+ {'eval_loss': 0.9322895407676697, 'eval_runtime': 61.47, 'eval_samples_per_second': 39.011, 'eval_steps_per_second': 4.88, 'epoch': 0.96}
103
+ {'loss': 0.8693, 'grad_norm': 1.390625, 'learning_rate': 1.6515209139561796e-05, 'epoch': 0.98}
104
+ {'loss': 0.923, 'grad_norm': 1.484375, 'learning_rate': 1.642271247650136e-05, 'epoch': 0.99}
105
+ {'loss': 0.9334, 'grad_norm': 1.40625, 'learning_rate': 1.6329270853554807e-05, 'epoch': 1.0}
106
+ {'loss': 0.8209, 'grad_norm': 1.625, 'learning_rate': 1.6234898018587336e-05, 'epoch': 1.01}
107
+ {'loss': 0.819, 'grad_norm': 1.484375, 'learning_rate': 1.6139607856471377e-05, 'epoch': 1.02}
108
+ {'loss': 0.8783, 'grad_norm': 1.4140625, 'learning_rate': 1.604341438704373e-05, 'epoch': 1.03}
109
+ {'loss': 0.8592, 'grad_norm': 1.484375, 'learning_rate': 1.594633176304287e-05, 'epoch': 1.04}
110
+ {'loss': 0.7704, 'grad_norm': 1.4921875, 'learning_rate': 1.5848374268026647e-05, 'epoch': 1.05}
111
+ {'loss': 0.8401, 'grad_norm': 1.4921875, 'learning_rate': 1.574955631427083e-05, 'epoch': 1.06}
112
+ {'loss': 0.8882, 'grad_norm': 1.5, 'learning_rate': 1.5649892440648625e-05, 'epoch': 1.07}
113
+ {'eval_loss': 0.9229800701141357, 'eval_runtime': 61.534, 'eval_samples_per_second': 38.97, 'eval_steps_per_second': 4.875, 'epoch': 1.07}
114
+ {'loss': 0.8254, 'grad_norm': 1.453125, 'learning_rate': 1.5549397310491605e-05, 'epoch': 1.08}
115
+ {'loss': 0.8703, 'grad_norm': 1.46875, 'learning_rate': 1.5448085709432338e-05, 'epoch': 1.09}
116
+ {'loss': 0.8834, 'grad_norm': 1.375, 'learning_rate': 1.5345972543229e-05, 'epoch': 1.1}
117
+ {'loss': 0.8844, 'grad_norm': 1.390625, 'learning_rate': 1.5243072835572319e-05, 'epoch': 1.11}
118
+ {'loss': 0.7802, 'grad_norm': 1.359375, 'learning_rate': 1.513940172587518e-05, 'epoch': 1.13}
119
+ {'loss': 0.8595, 'grad_norm': 1.3984375, 'learning_rate': 1.50349744670452e-05, 'epoch': 1.14}
120
+ {'loss': 0.791, 'grad_norm': 1.4453125, 'learning_rate': 1.4929806423240582e-05, 'epoch': 1.15}
121
+ {'loss': 0.8502, 'grad_norm': 1.6015625, 'learning_rate': 1.4823913067609639e-05, 'epoch': 1.16}
122
+ {'loss': 0.8405, 'grad_norm': 1.359375, 'learning_rate': 1.4717309980014245e-05, 'epoch': 1.17}
123
+ {'loss': 0.8586, 'grad_norm': 1.3359375, 'learning_rate': 1.4610012844737622e-05, 'epoch': 1.18}
124
+ {'eval_loss': 0.9161081910133362, 'eval_runtime': 61.5281, 'eval_samples_per_second': 38.974, 'eval_steps_per_second': 4.876, 'epoch': 1.18}
125
+ {'loss': 0.8359, 'grad_norm': 1.46875, 'learning_rate': 1.4502037448176734e-05, 'epoch': 1.19}
126
+ {'loss': 0.8696, 'grad_norm': 1.421875, 'learning_rate': 1.4393399676519668e-05, 'epoch': 1.2}
127
+ {'loss': 0.85, 'grad_norm': 1.4453125, 'learning_rate': 1.4284115513408337e-05, 'epoch': 1.21}
128
+ {'loss': 0.832, 'grad_norm': 1.421875, 'learning_rate': 1.4174201037586841e-05, 'epoch': 1.22}
129
+ {'loss': 0.8482, 'grad_norm': 1.2265625, 'learning_rate': 1.406367242053583e-05, 'epoch': 1.23}
130
+ {'loss': 0.7783, 'grad_norm': 1.3359375, 'learning_rate': 1.3952545924093239e-05, 'epoch': 1.24}
131
+ {'loss': 0.8102, 'grad_norm': 1.34375, 'learning_rate': 1.3840837898061711e-05, 'epoch': 1.25}
132
+ {'loss': 0.8828, 'grad_norm': 1.3046875, 'learning_rate': 1.3728564777803089e-05, 'epoch': 1.26}
133
+ {'loss': 0.8835, 'grad_norm': 1.265625, 'learning_rate': 1.361574308182031e-05, 'epoch': 1.28}
134
+ {'loss': 0.8041, 'grad_norm': 1.3203125, 'learning_rate': 1.3502389409327087e-05, 'epoch': 1.29}
135
+ {'eval_loss': 0.9101383090019226, 'eval_runtime': 61.518, 'eval_samples_per_second': 38.98, 'eval_steps_per_second': 4.877, 'epoch': 1.29}
136
+ {'loss': 0.845, 'grad_norm': 1.3125, 'learning_rate': 1.338852043780569e-05, 'epoch': 1.3}
137
+ {'loss': 0.792, 'grad_norm': 1.2890625, 'learning_rate': 1.3274152920553225e-05, 'epoch': 1.31}
138
+ {'loss': 0.8296, 'grad_norm': 1.40625, 'learning_rate': 1.3159303684216761e-05, 'epoch': 1.32}
139
+ {'loss': 0.8219, 'grad_norm': 1.2734375, 'learning_rate': 1.3043989626317668e-05, 'epoch': 1.33}
140
+ {'loss': 0.7972, 'grad_norm': 1.28125, 'learning_rate': 1.2928227712765504e-05, 'epoch': 1.34}
141
+ {'loss': 0.7935, 'grad_norm': 1.296875, 'learning_rate': 1.2812034975361876e-05, 'epoch': 1.35}
142
+ {'loss': 0.7807, 'grad_norm': 1.3046875, 'learning_rate': 1.2695428509294567e-05, 'epoch': 1.36}
143
+ {'loss': 0.7883, 'grad_norm': 1.4375, 'learning_rate': 1.257842547062238e-05, 'epoch': 1.37}
144
+ {'loss': 0.8166, 'grad_norm': 1.421875, 'learning_rate': 1.2461043073750988e-05, 'epoch': 1.38}
145
+ {'loss': 0.8, 'grad_norm': 1.3125, 'learning_rate': 1.2343298588900226e-05, 'epoch': 1.39}
146
+ {'eval_loss': 0.9054111838340759, 'eval_runtime': 61.4541, 'eval_samples_per_second': 39.021, 'eval_steps_per_second': 4.882, 'epoch': 1.39}
147
+ {'loss': 0.8647, 'grad_norm': 1.3046875, 'learning_rate': 1.2225209339563144e-05, 'epoch': 1.4}
148
+ {'loss': 0.82, 'grad_norm': 1.296875, 'learning_rate': 1.2106792699957264e-05, 'epoch': 1.41}
149
+ {'loss': 0.8504, 'grad_norm': 1.328125, 'learning_rate': 1.1988066092468325e-05, 'epoch': 1.43}
150
+ {'loss': 0.9289, 'grad_norm': 1.375, 'learning_rate': 1.1869046985086978e-05, 'epoch': 1.44}
151
+ {'loss': 0.8126, 'grad_norm': 1.2734375, 'learning_rate': 1.1749752888838754e-05, 'epoch': 1.45}
152
+ {'loss': 0.8081, 'grad_norm': 1.25, 'learning_rate': 1.1630201355207709e-05, 'epoch': 1.46}
153
+ {'loss': 0.8005, 'grad_norm': 1.2421875, 'learning_rate': 1.15104099735541e-05, 'epoch': 1.47}
154
+ {'loss': 0.8247, 'grad_norm': 1.421875, 'learning_rate': 1.1390396368526518e-05, 'epoch': 1.48}
155
+ {'loss': 0.8029, 'grad_norm': 1.3984375, 'learning_rate': 1.1270178197468788e-05, 'epoch': 1.49}
156
+ {'loss': 0.866, 'grad_norm': 1.421875, 'learning_rate': 1.1149773147822112e-05, 'epoch': 1.5}
157
+ {'eval_loss': 0.9015324115753174, 'eval_runtime': 61.4764, 'eval_samples_per_second': 39.007, 'eval_steps_per_second': 4.88, 'epoch': 1.5}
158
+ {'loss': 0.7989, 'grad_norm': 1.234375, 'learning_rate': 1.1029198934522725e-05, 'epoch': 1.51}
159
+ {'loss': 0.7779, 'grad_norm': 1.328125, 'learning_rate': 1.0908473297395552e-05, 'epoch': 1.52}
160
+ {'loss': 0.8427, 'grad_norm': 1.265625, 'learning_rate': 1.0787613998544179e-05, 'epoch': 1.53}
161
+ {'loss': 0.7966, 'grad_norm': 1.2734375, 'learning_rate': 1.0666638819737554e-05, 'epoch': 1.54}
162
+ {'loss': 0.838, 'grad_norm': 1.2890625, 'learning_rate': 1.0545565559793796e-05, 'epoch': 1.55}
163
+ {'loss': 0.8277, 'grad_norm': 1.2265625, 'learning_rate': 1.0424412031961485e-05, 'epoch': 1.56}
164
+ {'loss': 0.8284, 'grad_norm': 1.28125, 'learning_rate': 1.030319606129885e-05, 'epoch': 1.58}
165
+ {'loss': 0.8144, 'grad_norm': 1.296875, 'learning_rate': 1.0181935482051198e-05, 'epoch': 1.59}
166
+ {'loss': 0.8051, 'grad_norm': 1.3203125, 'learning_rate': 1.0060648135026999e-05, 'epoch': 1.6}
167
+ {'loss': 0.8046, 'grad_norm': 1.2421875, 'learning_rate': 9.939351864973006e-06, 'epoch': 1.61}
168
+ {'eval_loss': 0.8985607028007507, 'eval_runtime': 61.4642, 'eval_samples_per_second': 39.015, 'eval_steps_per_second': 4.881, 'epoch': 1.61}
169
+ {'loss': 0.8203, 'grad_norm': 1.296875, 'learning_rate': 9.818064517948806e-06, 'epoch': 1.62}
170
+ {'loss': 0.8391, 'grad_norm': 1.3671875, 'learning_rate': 9.696803938701153e-06, 'epoch': 1.63}
171
+ {'loss': 0.8207, 'grad_norm': 1.28125, 'learning_rate': 9.57558796803852e-06, 'epoch': 1.64}
172
+ {'loss': 0.8139, 'grad_norm': 1.2578125, 'learning_rate': 9.454434440206211e-06, 'epoch': 1.65}
173
+ {'loss': 0.8507, 'grad_norm': 1.2265625, 'learning_rate': 9.33336118026245e-06, 'epoch': 1.66}
174
+ {'loss': 0.8363, 'grad_norm': 1.234375, 'learning_rate': 9.212386001455826e-06, 'epoch': 1.67}
175
+ {'loss': 0.8104, 'grad_norm': 1.2421875, 'learning_rate': 9.091526702604448e-06, 'epoch': 1.68}
176
+ {'loss': 0.8182, 'grad_norm': 1.2265625, 'learning_rate': 8.970801065477276e-06, 'epoch': 1.69}
177
+ {'loss': 0.8069, 'grad_norm': 1.2109375, 'learning_rate': 8.85022685217789e-06, 'epoch': 1.7}
178
+ {'loss': 0.7971, 'grad_norm': 1.2265625, 'learning_rate': 8.729821802531213e-06, 'epoch': 1.71}
179
+ {'eval_loss': 0.8961145877838135, 'eval_runtime': 61.4613, 'eval_samples_per_second': 39.016, 'eval_steps_per_second': 4.881, 'epoch': 1.71}
180
+ {'loss': 0.8146, 'grad_norm': 1.265625, 'learning_rate': 8.609603631473487e-06, 'epoch': 1.73}
181
+ {'loss': 0.8345, 'grad_norm': 1.25, 'learning_rate': 8.489590026445902e-06, 'epoch': 1.74}
182
+ {'loss': 0.8866, 'grad_norm': 1.2421875, 'learning_rate': 8.369798644792295e-06, 'epoch': 1.75}
183
+ {'loss': 0.8346, 'grad_norm': 1.21875, 'learning_rate': 8.250247111161248e-06, 'epoch': 1.76}
184
+ {'loss': 0.7941, 'grad_norm': 1.3125, 'learning_rate': 8.130953014913025e-06, 'epoch': 1.77}
185
+ {'loss': 0.7653, 'grad_norm': 1.1875, 'learning_rate': 8.01193390753168e-06, 'epoch': 1.78}
186
+ {'loss': 0.8379, 'grad_norm': 1.3046875, 'learning_rate': 7.89320730004274e-06, 'epoch': 1.79}
187
+ {'loss': 0.7325, 'grad_norm': 1.1640625, 'learning_rate': 7.774790660436857e-06, 'epoch': 1.8}
188
+ {'loss': 0.7441, 'grad_norm': 1.2109375, 'learning_rate': 7.656701411099777e-06, 'epoch': 1.81}
189
+ {'loss': 0.8323, 'grad_norm': 1.265625, 'learning_rate': 7.538956926249013e-06, 'epoch': 1.82}
190
+ {'eval_loss': 0.8942956328392029, 'eval_runtime': 61.4934, 'eval_samples_per_second': 38.996, 'eval_steps_per_second': 4.879, 'epoch': 1.82}
191
+ {'loss': 0.8577, 'grad_norm': 1.234375, 'learning_rate': 7.421574529377623e-06, 'epoch': 1.83}
192
+ {'loss': 0.8057, 'grad_norm': 1.2265625, 'learning_rate': 7.3045714907054345e-06, 'epoch': 1.84}
193
+ {'loss': 0.8473, 'grad_norm': 1.25, 'learning_rate': 7.187965024638127e-06, 'epoch': 1.85}
194
+ {'loss': 0.805, 'grad_norm': 1.2109375, 'learning_rate': 7.071772287234497e-06, 'epoch': 1.86}
195
+ {'loss': 0.8014, 'grad_norm': 1.25, 'learning_rate': 6.956010373682334e-06, 'epoch': 1.88}
196
+ {'loss': 0.8308, 'grad_norm': 1.25, 'learning_rate': 6.840696315783239e-06, 'epoch': 1.89}
197
+ {'loss': 0.7863, 'grad_norm': 1.2578125, 'learning_rate': 6.725847079446779e-06, 'epoch': 1.9}
198
+ {'loss': 0.7806, 'grad_norm': 1.2578125, 'learning_rate': 6.611479562194314e-06, 'epoch': 1.91}
199
+ {'loss': 0.82, 'grad_norm': 1.1875, 'learning_rate': 6.497610590672916e-06, 'epoch': 1.92}
200
+ {'loss': 0.7982, 'grad_norm': 1.203125, 'learning_rate': 6.384256918179692e-06, 'epoch': 1.93}
201
+ {'eval_loss': 0.8930652141571045, 'eval_runtime': 61.5038, 'eval_samples_per_second': 38.989, 'eval_steps_per_second': 4.878, 'epoch': 1.93}
202
+ {'loss': 0.8593, 'grad_norm': 1.375, 'learning_rate': 6.2714352221969155e-06, 'epoch': 1.94}
203
+ {'loss': 0.7895, 'grad_norm': 1.171875, 'learning_rate': 6.159162101938292e-06, 'epoch': 1.95}
204
+ {'loss': 0.8173, 'grad_norm': 1.3359375, 'learning_rate': 6.0474540759067645e-06, 'epoch': 1.96}
205
+ {'loss': 0.7539, 'grad_norm': 1.1953125, 'learning_rate': 5.936327579464174e-06, 'epoch': 1.97}
206
+ {'loss': 0.7988, 'grad_norm': 1.2734375, 'learning_rate': 5.825798962413164e-06, 'epoch': 1.98}
207
+ {'loss': 0.8028, 'grad_norm': 1.2265625, 'learning_rate': 5.715884486591663e-06, 'epoch': 1.99}
208
+ {'loss': 0.7474, 'grad_norm': 1.21875, 'learning_rate': 5.606600323480332e-06, 'epoch': 2.0}
209
+ {'loss': 0.756, 'grad_norm': 1.2265625, 'learning_rate': 5.497962551823266e-06, 'epoch': 2.01}
210
+ {'loss': 0.8065, 'grad_norm': 1.2109375, 'learning_rate': 5.38998715526238e-06, 'epoch': 2.03}
211
+ {'loss': 0.7936, 'grad_norm': 1.2265625, 'learning_rate': 5.282690019985756e-06, 'epoch': 2.04}
212
+ {'eval_loss': 0.8921071290969849, 'eval_runtime': 61.521, 'eval_samples_per_second': 38.979, 'eval_steps_per_second': 4.876, 'epoch': 2.04}
213
+ {'loss': 0.8441, 'grad_norm': 1.2109375, 'learning_rate': 5.176086932390365e-06, 'epoch': 2.05}
214
+ {'loss': 0.8159, 'grad_norm': 1.2421875, 'learning_rate': 5.070193576759419e-06, 'epoch': 2.06}
215
+ {'loss': 0.7595, 'grad_norm': 1.21875, 'learning_rate': 4.9650255329548016e-06, 'epoch': 2.07}
216
+ {'loss': 0.7534, 'grad_norm': 1.1875, 'learning_rate': 4.860598274124821e-06, 'epoch': 2.08}
217
+ {'loss': 0.798, 'grad_norm': 1.1953125, 'learning_rate': 4.756927164427685e-06, 'epoch': 2.09}
218
+ {'loss': 0.8096, 'grad_norm': 1.21875, 'learning_rate': 4.6540274567710044e-06, 'epoch': 2.1}
219
+ {'loss': 0.8322, 'grad_norm': 1.234375, 'learning_rate': 4.551914290567665e-06, 'epoch': 2.11}
220
+ {'loss': 0.7773, 'grad_norm': 1.21875, 'learning_rate': 4.450602689508399e-06, 'epoch': 2.12}
221
+ {'loss': 0.7621, 'grad_norm': 1.2421875, 'learning_rate': 4.35010755935138e-06, 'epoch': 2.13}
222
+ {'loss': 0.7822, 'grad_norm': 1.1640625, 'learning_rate': 4.25044368572917e-06, 'epoch': 2.14}
223
+ {'eval_loss': 0.8922712802886963, 'eval_runtime': 61.5132, 'eval_samples_per_second': 38.984, 'eval_steps_per_second': 4.877, 'epoch': 2.14}
224
+ {'loss': 0.7957, 'grad_norm': 1.2421875, 'learning_rate': 4.151625731973354e-06, 'epoch': 2.15}
225
+ {'loss': 0.7848, 'grad_norm': 1.1796875, 'learning_rate': 4.053668236957135e-06, 'epoch': 2.16}
226
+ {'loss': 0.8107, 'grad_norm': 1.234375, 'learning_rate': 3.956585612956268e-06, 'epoch': 2.18}
227
+ {'loss': 0.788, 'grad_norm': 1.21875, 'learning_rate': 3.860392143528624e-06, 'epoch': 2.19}
228
+ {'loss': 0.7249, 'grad_norm': 1.2109375, 'learning_rate': 3.7651019814126656e-06, 'epoch': 2.2}
229
+ {'loss': 0.7649, 'grad_norm': 1.1640625, 'learning_rate': 3.6707291464451953e-06, 'epoch': 2.21}
230
+ {'loss': 0.8103, 'grad_norm': 1.21875, 'learning_rate': 3.5772875234986413e-06, 'epoch': 2.22}
231
+ {'loss': 0.774, 'grad_norm': 1.1953125, 'learning_rate': 3.4847908604382095e-06, 'epoch': 2.23}
232
+ {'loss': 0.8141, 'grad_norm': 1.203125, 'learning_rate': 3.3932527660991877e-06, 'epoch': 2.24}
233
+ {'loss': 0.773, 'grad_norm': 1.1953125, 'learning_rate': 3.3026867082847058e-06, 'epoch': 2.25}
234
+ {'eval_loss': 0.8915932178497314, 'eval_runtime': 61.5129, 'eval_samples_per_second': 38.984, 'eval_steps_per_second': 4.877, 'epoch': 2.25}
235
+ {'loss': 0.771, 'grad_norm': 1.1875, 'learning_rate': 3.2131060117842505e-06, 'epoch': 2.26}
236
+ {'loss': 0.7832, 'grad_norm': 1.1953125, 'learning_rate': 3.124523856413216e-06, 'epoch': 2.27}
237
+ {'loss': 0.7763, 'grad_norm': 1.1796875, 'learning_rate': 3.036953275073783e-06, 'epoch': 2.28}
238
+ {'loss': 0.8106, 'grad_norm': 1.234375, 'learning_rate': 2.950407151837421e-06, 'epoch': 2.29}
239
+ {'loss': 0.7779, 'grad_norm': 1.1796875, 'learning_rate': 2.864898220049277e-06, 'epoch': 2.3}
240
+ {'loss': 0.7643, 'grad_norm': 1.1953125, 'learning_rate': 2.780439060454756e-06, 'epoch': 2.31}
241
+ {'loss': 0.7708, 'grad_norm': 1.1796875, 'learning_rate': 2.697042099348528e-06, 'epoch': 2.33}
242
+ {'loss': 0.8141, 'grad_norm': 1.1875, 'learning_rate': 2.6147196067462855e-06, 'epoch': 2.34}
243
+ {'loss': 0.7888, 'grad_norm': 1.15625, 'learning_rate': 2.533483694579477e-06, 'epoch': 2.35}
244
+ {'loss': 0.8109, 'grad_norm': 1.1953125, 'learning_rate': 2.4533463149133073e-06, 'epoch': 2.36}
245
+ {'eval_loss': 0.8914577960968018, 'eval_runtime': 61.488, 'eval_samples_per_second': 38.999, 'eval_steps_per_second': 4.879, 'epoch': 2.36}
246
+ {'loss': 0.8304, 'grad_norm': 1.2109375, 'learning_rate': 2.3743192581882557e-06, 'epoch': 2.37}
247
+ {'loss': 0.7515, 'grad_norm': 1.21875, 'learning_rate': 2.296414151485371e-06, 'epoch': 2.38}
248
+ {'loss': 0.8105, 'grad_norm': 1.1953125, 'learning_rate': 2.2196424568156073e-06, 'epoch': 2.39}
249
+ {'loss': 0.8525, 'grad_norm': 1.1484375, 'learning_rate': 2.14401546943344e-06, 'epoch': 2.4}
250
+ {'loss': 0.8118, 'grad_norm': 1.15625, 'learning_rate': 2.069544316175025e-06, 'epoch': 2.41}
251
+ {'loss': 0.7995, 'grad_norm': 1.1796875, 'learning_rate': 1.996239953821121e-06, 'epoch': 2.42}
252
+ {'loss': 0.8049, 'grad_norm': 1.125, 'learning_rate': 1.924113167485054e-06, 'epoch': 2.43}
253
+ {'loss': 0.8064, 'grad_norm': 1.1796875, 'learning_rate': 1.853174569025914e-06, 'epoch': 2.44}
254
+ {'loss': 0.8134, 'grad_norm': 1.15625, 'learning_rate': 1.7834345954872711e-06, 'epoch': 2.45}
255
+ {'loss': 0.871, 'grad_norm': 1.1484375, 'learning_rate': 1.7149035075615795e-06, 'epoch': 2.46}
256
+ {'eval_loss': 0.8914534449577332, 'eval_runtime': 61.4915, 'eval_samples_per_second': 38.997, 'eval_steps_per_second': 4.879, 'epoch': 2.46}
257
+ {'loss': 0.8283, 'grad_norm': 1.1484375, 'learning_rate': 1.6475913880805516e-06, 'epoch': 2.48}
258
+ {'loss': 0.7995, 'grad_norm': 1.1875, 'learning_rate': 1.5815081405316912e-06, 'epoch': 2.49}
259
+ {'loss': 0.8053, 'grad_norm': 1.140625, 'learning_rate': 1.5166634876012187e-06, 'epoch': 2.5}
260
+ {'loss': 0.7625, 'grad_norm': 1.15625, 'learning_rate': 1.4530669697435861e-06, 'epoch': 2.51}
261
+ {'loss': 0.8122, 'grad_norm': 1.1796875, 'learning_rate': 1.3907279437778154e-06, 'epoch': 2.52}
262
+ {'loss': 0.7702, 'grad_norm': 1.1953125, 'learning_rate': 1.329655581510847e-06, 'epoch': 2.53}
263
+ {'loss': 0.7737, 'grad_norm': 1.1875, 'learning_rate': 1.2698588683881185e-06, 'epoch': 2.54}
264
+ {'loss': 0.7867, 'grad_norm': 1.203125, 'learning_rate': 1.2113466021715426e-06, 'epoch': 2.55}
265
+ {'loss': 0.8395, 'grad_norm': 1.1796875, 'learning_rate': 1.1541273916451234e-06, 'epoch': 2.56}
266
+ {'loss': 0.7567, 'grad_norm': 1.1953125, 'learning_rate': 1.0982096553483568e-06, 'epoch': 2.57}
267
+ {'eval_loss': 0.891376793384552, 'eval_runtime': 61.4964, 'eval_samples_per_second': 38.994, 'eval_steps_per_second': 4.878, 'epoch': 2.57}
268
+ {'loss': 0.7879, 'grad_norm': 1.1640625, 'learning_rate': 1.0436016203376343e-06, 'epoch': 2.58}
269
+ {'loss': 0.811, 'grad_norm': 1.203125, 'learning_rate': 9.903113209758098e-07, 'epoch': 2.59}
270
+ {'loss': 0.7863, 'grad_norm': 1.1640625, 'learning_rate': 9.383465977501227e-07, 'epoch': 2.6}
271
+ {'loss': 0.781, 'grad_norm': 1.1640625, 'learning_rate': 8.87715096118642e-07, 'epoch': 2.61}
272
+ {'loss': 0.7732, 'grad_norm': 1.1875, 'learning_rate': 8.384242653854146e-07, 'epoch': 2.63}
273
+ {'loss': 0.7536, 'grad_norm': 1.1640625, 'learning_rate': 7.904813576044534e-07, 'epoch': 2.64}
274
+ {'loss': 0.8053, 'grad_norm': 1.1875, 'learning_rate': 7.43893426512764e-07, 'epoch': 2.65}
275
+ {'loss': 0.7744, 'grad_norm': 1.1796875, 'learning_rate': 6.986673264925437e-07, 'epoch': 2.66}
276
+ {'loss': 0.7253, 'grad_norm': 1.21875, 'learning_rate': 6.548097115627106e-07, 'epoch': 2.67}
277
+ {'loss': 0.7816, 'grad_norm': 1.1953125, 'learning_rate': 6.123270343999132e-07, 'epoch': 2.68}
278
+ {'eval_loss': 0.8913903832435608, 'eval_runtime': 61.5028, 'eval_samples_per_second': 38.99, 'eval_steps_per_second': 4.878, 'epoch': 2.68}
279
+ {'loss': 0.8443, 'grad_norm': 1.1484375, 'learning_rate': 5.71225545389158e-07, 'epoch': 2.69}
280
+ {'loss': 0.8282, 'grad_norm': 1.25, 'learning_rate': 5.315112917042097e-07, 'epoch': 2.7}
281
+ {'loss': 0.7686, 'grad_norm': 1.1796875, 'learning_rate': 4.931901164178765e-07, 'epoch': 2.71}
282
+ {'loss': 0.8373, 'grad_norm': 1.1953125, 'learning_rate': 4.562676576423397e-07, 'epoch': 2.72}
283
+ {'loss': 0.7696, 'grad_norm': 1.1484375, 'learning_rate': 4.207493476996205e-07, 'epoch': 2.73}
284
+ {'loss': 0.8061, 'grad_norm': 1.1953125, 'learning_rate': 3.866404123223444e-07, 'epoch': 2.74}
285
+ {'loss': 0.8311, 'grad_norm': 1.1640625, 'learning_rate': 3.53945869884883e-07, 'epoch': 2.75}
286
+ {'loss': 0.7351, 'grad_norm': 1.171875, 'learning_rate': 3.226705306650113e-07, 'epoch': 2.76}
287
+ {'loss': 0.7752, 'grad_norm': 1.2109375, 'learning_rate': 2.9281899613619047e-07, 'epoch': 2.78}
288
+ {'loss': 0.7619, 'grad_norm': 1.171875, 'learning_rate': 2.6439565829055267e-07, 'epoch': 2.79}
289
+ {'eval_loss': 0.8913276791572571, 'eval_runtime': 61.4895, 'eval_samples_per_second': 38.999, 'eval_steps_per_second': 4.879, 'epoch': 2.79}
290
+ {'loss': 0.7793, 'grad_norm': 1.2109375, 'learning_rate': 2.3740469899272144e-07, 'epoch': 2.8}
291
+ {'loss': 0.8276, 'grad_norm': 1.1484375, 'learning_rate': 2.1185008936454253e-07, 'epoch': 2.81}
292
+ {'loss': 0.7787, 'grad_norm': 1.1875, 'learning_rate': 1.8773558920082037e-07, 'epoch': 2.82}
293
+ {'loss': 0.7665, 'grad_norm': 1.1953125, 'learning_rate': 1.6506474641614923e-07, 'epoch': 2.83}
294
+ {'loss': 0.766, 'grad_norm': 1.1328125, 'learning_rate': 1.4384089652291544e-07, 'epoch': 2.84}
295
+ {'loss': 0.7885, 'grad_norm': 1.125, 'learning_rate': 1.2406716214054982e-07, 'epoch': 2.85}
296
+ {'loss': 0.7688, 'grad_norm': 1.1484375, 'learning_rate': 1.0574645253610405e-07, 'epoch': 2.86}
297
+ {'loss': 0.8491, 'grad_norm': 1.1328125, 'learning_rate': 8.888146319621538e-08, 'epoch': 2.87}
298
+ {'loss': 0.7896, 'grad_norm': 1.1796875, 'learning_rate': 7.347467543052932e-08, 'epoch': 2.88}
299
+ {'loss': 0.8123, 'grad_norm': 1.1875, 'learning_rate': 5.952835600662288e-08, 'epoch': 2.89}
special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "[PAD]"
17
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,2071 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ },
2051
+ "128256": {
2052
+ "content": "[PAD]",
2053
+ "lstrip": false,
2054
+ "normalized": false,
2055
+ "rstrip": false,
2056
+ "single_word": false,
2057
+ "special": true
2058
+ }
2059
+ },
2060
+ "bos_token": "<|begin_of_text|>",
2061
+ "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- if strftime_now is defined %}\n {%- set date_string = strftime_now(\"%d %b %Y\") %}\n {%- else %}\n {%- set date_string = \"26 Jul 2024\" %}\n {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {{- \"<|eot_id|>\" }}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
2062
+ "clean_up_tokenization_spaces": true,
2063
+ "eos_token": "<|eot_id|>",
2064
+ "model_input_names": [
2065
+ "input_ids",
2066
+ "attention_mask"
2067
+ ],
2068
+ "model_max_length": 1024,
2069
+ "pad_token": "[PAD]",
2070
+ "tokenizer_class": "PreTrainedTokenizerFast"
2071
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9386f8678398de2408a559b4db426fb9df08b21d9fd7430ef1c0a8aea9f6c0d9
3
+ size 5496